INDEX

Explanations

proper nouns related to individuals and organizations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amen

-0.51

 nene

-0.50

MOST

-0.49

OPO

-0.49

st

-0.49

 Ersten

-0.48

prese

-0.46

 original

-0.46

DebuggerNonUser

-0.46

 nonatomic

-0.45

POSITIVE LOGITS

 AssemblyProduct

0.74

 betweenstory

0.71

EndContext

0.64

otras

0.63

 Italijanski

0.61

ThroughAttribute

0.61

 piaggio

0.59

 margiela

0.58

uxxxx

0.57

Efq

0.57

Activations Density 0.167%

proper nouns related to individuals and organizations

No Comments

No Known Activations